agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH v4 2/3] remove lo_hton64() and lo_ntoh64() 1105+ messages / 2 participants [nested] [flat]
* [PATCH v4 2/3] remove lo_hton64() and lo_ntoh64() @ 2026-06-02 17:22 Reviewer <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Reviewer @ 2026-06-02 17:22 UTC (permalink / raw) --- src/interfaces/libpq/fe-lobj.c | 58 +++------------------------------- 1 file changed, 4 insertions(+), 54 deletions(-) diff --git a/src/interfaces/libpq/fe-lobj.c b/src/interfaces/libpq/fe-lobj.c index 1660c969f58..42b2a36bda9 100644 --- a/src/interfaces/libpq/fe-lobj.c +++ b/src/interfaces/libpq/fe-lobj.c @@ -43,8 +43,6 @@ static int lo_initialize(PGconn *conn); static Oid lo_import_internal(PGconn *conn, const char *filename, Oid oid); -static int64_t lo_hton64(int64_t host64); -static int64_t lo_ntoh64(int64_t net64); /* * lo_open @@ -213,7 +211,7 @@ lo_truncate64(PGconn *conn, int fd, int64_t len) argv[0].len = 4; argv[0].u.integer = fd; - len = lo_hton64(len); + len = pg_hton64(len); argv[1].isint = 0; argv[1].len = 8; argv[1].u.ptr = (int *) &len; @@ -403,7 +401,7 @@ lo_lseek64(PGconn *conn, int fd, int64_t offset, int whence) argv[0].len = 4; argv[0].u.integer = fd; - offset = lo_hton64(offset); + offset = pg_hton64(offset); argv[1].isint = 0; argv[1].len = 8; argv[1].u.ptr = (int *) &offset; @@ -417,7 +415,7 @@ lo_lseek64(PGconn *conn, int fd, int64_t offset, int whence) if (PQresultStatus(res) == PGRES_COMMAND_OK && result_len == 8) { PQclear(res); - return lo_ntoh64(retval); + return pg_ntoh64(retval); } else { @@ -571,7 +569,7 @@ lo_tell64(PGconn *conn, int fd) if (PQresultStatus(res) == PGRES_COMMAND_OK && result_len == 8) { PQclear(res); - return lo_ntoh64(retval); + return pg_ntoh64(retval); } else { @@ -1014,51 +1012,3 @@ lo_initialize(PGconn *conn) conn->lobjfuncs = lobjfuncs; return 0; } - -/* - * lo_hton64 - * converts a 64-bit integer from host byte order to network byte order - */ -static int64_t -lo_hton64(int64_t host64) -{ - union - { - int64 i64; - uint32 i32[2]; - } swap; - uint32 t; - - /* High order half first, since we're doing MSB-first */ - t = (uint32) (host64 >> 32); - swap.i32[0] = pg_hton32(t); - - /* Now the low order half */ - t = (uint32) host64; - swap.i32[1] = pg_hton32(t); - - return swap.i64; -} - -/* - * lo_ntoh64 - * converts a 64-bit integer from network byte order to host byte order - */ -static int64_t -lo_ntoh64(int64_t net64) -{ - union - { - int64 i64; - uint32 i32[2]; - } swap; - int64 result; - - swap.i64 = net64; - - result = (uint32) pg_ntoh32(swap.i32[0]); - result <<= 32; - result |= (uint32) pg_ntoh32(swap.i32[1]); - - return result; -} -- 2.50.1 (Apple Git-155) --Z10p9YYojB0/BzD2 Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v4-0003-add-helper-functions-for-fast-path-arg-setup.patch ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-03 14:03 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++------- 1 file changed, 118 insertions(+), 49 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index e23b366a87d..866341c2cfb 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) form = (Form_pg_subscription) GETSTRUCT(tup); subid = form->oid; - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - /* DROP hook for the subscription being removed */ InvokeObjectDropHook(SubscriptionRelationId, subid, 0); @@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); + + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; -- 2.34.1 --3eAVwo4vDNlHc8RC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --3eAVwo4vDNlHc8RC-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication @ 2026-07-03 14:46 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw) Apply the same RangeVarGetRelidExtended() style retry loop to AlterPublication()'s tables/schemas branch that was added for subscriptions in commit XXXX. Previously, this branch resolved the publication name and checked ownership at the top of AlterPublication(), then locked and re-read by OID. This left a window where concurrent DDL could have modified the ownership and/or the name resolution Now the tables/schemas branch has its own complete retry loop: name resolution, ownership check, and lock acquisition all inside the loop. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/publicationcmds.c | 105 +++++++++++++++++-------- 1 file changed, 72 insertions(+), 33 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c index 440adb356ad..dfd707bc7d7 100644 --- a/src/backend/commands/publicationcmds.c +++ b/src/backend/commands/publicationcmds.c @@ -39,6 +39,7 @@ #include "parser/parse_relation.h" #include "rewrite/rewriteHandler.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/inval.h" @@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt) rel = table_open(PublicationRelationId, RowExclusiveLock); - tup = SearchSysCacheCopy1(PUBLICATIONNAME, - CStringGetDatum(stmt->pubname)); + if (stmt->options) + { + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname))); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - pubform = (Form_pg_publication) GETSTRUCT(tup); + pubform = (Form_pg_publication) GETSTRUCT(tup); - /* must be owner */ - if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, - stmt->pubname); + /* must be owner */ + if (!object_ownercheck(PublicationRelationId, pubform->oid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); - if (stmt->options) AlterPublicationOptions(pstate, stmt, rel, tup); + } else { List *relations = NIL; List *exceptrelations = NIL; List *schemaidlist = NIL; - Oid pubid = pubform->oid; + Oid pubid; - ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, - &exceptrelations, &schemaidlist); + /* + * Lock the publication so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation + * messages arrive (indicating concurrent DDL), we retry. We keep the + * lock held across retries and only release it if the name resolves + * to a different OID on the next iteration. + */ + { + Oid oldPubId = InvalidOid; + bool retry = false; - CheckAlterPublication(stmt, tup, relations, schemaidlist); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - heap_freetuple(tup); + tup = SearchSysCacheCopy1(PUBLICATIONNAME, + CStringGetDatum(stmt->pubname)); - /* Lock the publication so nobody else can do anything with it. */ - LockDatabaseObject(PublicationRelationId, pubid, 0, - AccessExclusiveLock); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("publication \"%s\" does not exist", + stmt->pubname))); - /* - * It is possible that by the time we acquire the lock on publication, - * concurrent DDL has removed it. We can test this by checking the - * existence of publication. We get the tuple again to avoid the risk - * of any publication option getting changed. - */ - tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("publication \"%s\" does not exist", - stmt->pubname)); + pubform = (Form_pg_publication) GETSTRUCT(tup); + pubid = pubform->oid; + + if (!object_ownercheck(PublicationRelationId, pubid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION, + stmt->pubname); + + if (retry) + { + if (pubid == oldPubId) + break; + UnlockDatabaseObject(PublicationRelationId, oldPubId, 0, + AccessExclusiveLock); + } + + LockDatabaseObject(PublicationRelationId, pubid, 0, + AccessExclusiveLock); + + if (inval_count == SharedInvalidMessageCounter) + break; + + retry = true; + oldPubId = pubid; + heap_freetuple(tup); + } + } + + ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations, + &exceptrelations, &schemaidlist); + + CheckAlterPublication(stmt, tup, relations, schemaidlist); relations = list_concat(relations, exceptrelations); AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext, -- 2.34.1 --b+bwjVhifbzgesmw-- ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
* [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription @ 2026-07-06 04:44 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 1105+ messages in thread From: Bertrand Drouvot @ 2026-07-06 04:44 UTC (permalink / raw) Following the approach of RangeVarGetRelidExtended() for relations, add a retry loop that includes name resolution, ownership check, and lock acquisition in AlterSubscription() and DropSubscription(). The loop records SharedInvalidMessageCounter, resolves the subscription name to an OID, checks ownership, then locks the subscription. If the invalidation counter changed (indicating concurrent DDL), we save the current OID and retry. On the next iteration, if the name still resolves to the same OID, we're done (already holding the correct lock). If it resolves to a different OID, we release the old lock and acquire the new one. This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across retries to avoid a window where another session could have committed concurrent DDL modifying the ownership and/or the name resolution. Author: Bertrand Drouvot <[email protected]> Reviewed-by: Dilip Kumar <[email protected]> Reviewed-by: Hayato Kuroda (Fujitsu) <[email protected]> Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg --- src/backend/commands/subscriptioncmds.c | 189 +++++++++++++++++------- 1 file changed, 134 insertions(+), 55 deletions(-) 100.0% src/backend/commands/ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index c9e7fbdb47b..615c3921bc3 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -50,6 +50,7 @@ #include "replication/walsender.h" #include "replication/worker_internal.h" #include "storage/lmgr.h" +#include "storage/sinval.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, rel = table_open(SubscriptionRelationId, RowExclusiveLock); - /* Fetch the existing tuple. */ - tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId), - CStringGetDatum(stmt->subname)); + /* + * Lock the subscription so nobody else can do anything with it. + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. + */ + { + Oid oldSubId = InvalidOid; + bool retry = false; - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; + tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); + if (!HeapTupleIsValid(tup)) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + heap_freetuple(tup); + } + } /* parse and check options */ switch (stmt->kind) @@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, orig_conninfo_needed = false; } - heap_freetuple(tup); - - /* Lock the subscription so nobody else can do anything with it. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); - - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * DROP or ALTER may have committed before we acquired the lock. - */ - tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); - - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); - - form = (Form_pg_subscription) GETSTRUCT(tup); - /* * Skip ACL checks on the subscription's foreign server, if any. If * changing the server (or replacing it with a raw connection), then the @@ -2567,38 +2593,91 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel) return; } - form = (Form_pg_subscription) GETSTRUCT(tup); - subid = form->oid; - - /* must be owner */ - if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId())) - aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, - stmt->subname); - ReleaseSysCache(tup); /* * Lock the subscription so nobody else can do anything with it (including * the replication workers). + * + * Like RangeVarGetRelidExtended() does for relations, we resolve the + * name, check ownership, and lock inside a loop. If invalidation messages + * arrive (indicating concurrent DDL), we retry. We keep the lock held + * across retries and only release it if the name resolves to a different + * OID on the next iteration. */ - LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock); + { + Oid oldSubId = InvalidOid; + bool retry = false; - /* DROP hook for the subscription being removed */ - InvokeObjectDropHook(SubscriptionRelationId, subid, 0); + for (;;) + { + uint64 inval_count = SharedInvalidMessageCounter; - /* - * Re-read the subscription tuple after acquiring the lock. A concurrent - * ALTER or DROP may have committed before we acquired the lock. - */ - tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid)); + tup = SearchSysCache2(SUBSCRIPTIONNAME, + ObjectIdGetDatum(MyDatabaseId), + CStringGetDatum(stmt->subname)); - if (!HeapTupleIsValid(tup)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("subscription \"%s\" does not exist", - stmt->subname))); + if (!HeapTupleIsValid(tup)) + { + if (retry) + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + table_close(rel, NoLock); + + if (!stmt->missing_ok) + ereport(ERROR, + (errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("subscription \"%s\" does not exist", + stmt->subname))); + else + ereport(NOTICE, + (errmsg("subscription \"%s\" does not exist, skipping", + stmt->subname))); + + return; + } + + form = (Form_pg_subscription) GETSTRUCT(tup); + subid = form->oid; + + if (!object_ownercheck(SubscriptionRelationId, subid, + GetUserId())) + { + ReleaseSysCache(tup); + aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION, + stmt->subname); + } + + /* + * If upon retry we get the same OID, the invalidation messages + * did not change the final answer. So we're done. If we got a + * different OID, unlock the old one and lock the new one below. + */ + if (retry) + { + if (subid == oldSubId) + break; + UnlockSharedObject(SubscriptionRelationId, oldSubId, 0, + AccessExclusiveLock); + } + + LockSharedObject(SubscriptionRelationId, subid, 0, + AccessExclusiveLock); + + /* If no invalidation messages, we're done. */ + if (inval_count == SharedInvalidMessageCounter) + break; + + /* Something may have changed, retry. */ + retry = true; + oldSubId = subid; + ReleaseSysCache(tup); + } + } + + /* DROP hook for the subscription being removed */ + InvokeObjectDropHook(SubscriptionRelationId, subid, 0); - form = (Form_pg_subscription) GETSTRUCT(tup); subowner = form->subowner; subserver = form->subserver; subconflictlogrelid = form->subconflictlogrelid; -- 2.34.1 --b+bwjVhifbzgesmw Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v4-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch" ^ permalink raw reply [nested|flat] 1105+ messages in thread
end of thread, other threads:[~2026-07-06 04:44 UTC | newest] Thread overview: 1105+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2026-06-02 17:22 [PATCH v4 2/3] remove lo_hton64() and lo_ntoh64() Reviewer <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]> 2026-07-06 04:44 [PATCH v4 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox