From dbca1d11d44dd57a5009ae31a0b94562a7e1d0af Mon Sep 17 00:00:00 2001 From: Bharath Rupireddy Date: Sat, 19 Sep 2026 06:04:37 +0000 Subject: [PATCH v19] Fix replication slot leak on error caught in a subtransaction. The SQL-callable replication slot functions, such as pg_replication_slot_advance(), acquire a slot and release it before returning. When one of them throws an error, the slot is normally released by the top-level error handler (the sigsetjmp block in PostgresMain()). But PL/pgSQL, PL/Perl, PL/Python and PL/Tcl run the statements they protect in an internal subtransaction, and when a matching handler catches the error there, it is never re-thrown and the top-level handler is never reached. Nothing on the (sub)transaction abort path releases the slot either, so it stays acquired. The next slot operation in the session then hits an assertion failure, or in a non-assertion build silently overwrites MyReplicationSlot. The leaked slot keeps holding back WAL removal and the catalog xmin, and can no longer be acquired. Fix this by recording the subtransaction that acquires the slot and releasing the slot when that subtransaction aborts. We cannot simply release the slot on every subtransaction abort, because logical decoding starts and aborts an internal (sub)transaction for each decoded transaction while holding the slot. Unlike the top-level handler, this path only releases the slot and doesn't drop the session's temporary slots. An error caught in a subtransaction is normally meant to be handled so that the session carries on, so we leave them in place, which is also what happened before this fix. Update the documentation accordingly. Note that a slot whose creation fails partway is still left behind holding resources, but that is a pre-existing problem not specific to subtransactions. Reported-by: SATYANARAYANA NARLAPURAM Author: Bharath Rupireddy Suggested-by: Masahiko Sawada Reviewed-by: Fujii Masao Reviewed-by: shveta malik Reviewed-by: Hou Zhijie Reviewed-by: Kyotaro Horiguchi Reviewed-by: Ashutosh Sharma Reviewed-by: Amit Kapila Reviewed-by: Chao Li Reviewed-by: kedar anavardekar Discussion: https://postgr.es/m/CAHg+QDeuf9tCq3ce=kgFMJP0m=PZC+wi6B=yS+7V0vNXjLS31w@mail.gmail.com Backpatch-through: 14 --- contrib/test_decoding/expected/slot.out | 89 +++++++++++++++++++++++++ contrib/test_decoding/sql/slot.sql | 46 +++++++++++++ doc/src/sgml/func/func-admin.sgml | 8 ++- doc/src/sgml/protocol.sgml | 5 +- doc/src/sgml/system-views.sgml | 5 +- src/backend/access/transam/xact.c | 2 + src/backend/replication/slot.c | 66 ++++++++++++++++++ src/backend/tcop/postgres.c | 4 +- src/include/replication/slot.h | 1 + 9 files changed, 221 insertions(+), 5 deletions(-) diff --git a/contrib/test_decoding/expected/slot.out b/contrib/test_decoding/expected/slot.out index cf0136455b0..53d8b445b23 100644 --- a/contrib/test_decoding/expected/slot.out +++ b/contrib/test_decoding/expected/slot.out @@ -469,3 +469,92 @@ SELECT pg_drop_replication_slot('physical_slot'); (1 row) +-- +-- Test that a replication slot gets released when the subtransaction holding +-- it aborts on an error caught by a PL/pgSQL exception block. +-- +SELECT 'init' FROM pg_create_logical_replication_slot('regress_subxact_slot', 'test_decoding'); + ?column? +---------- + init +(1 row) + +-- An error caught by a PL/pgSQL exception block releases the slot. +DO $$ +BEGIN + PERFORM pg_replication_slot_advance('regress_subxact_slot', '0/1'); +EXCEPTION WHEN OTHERS THEN + RAISE NOTICE 'caught SQLSTATE %', SQLSTATE; +END $$; +NOTICE: caught SQLSTATE 55000 +SELECT active FROM pg_replication_slots WHERE slot_name = 'regress_subxact_slot'; + active +-------- + f +(1 row) + +SELECT count(*) >= 0 AS peek_ok + FROM pg_logical_slot_peek_changes('regress_subxact_slot', NULL, NULL); + peek_ok +--------- + t +(1 row) + +-- An error not caught by a PL/pgSQL exception block releases the slot too. +-- Show only the SQLSTATE for stable output. +\set VERBOSITY sqlstate +DO $$ +BEGIN + PERFORM pg_replication_slot_advance('regress_subxact_slot', '0/1'); +EXCEPTION WHEN division_by_zero THEN + RAISE NOTICE 'unreachable'; +END $$; +ERROR: 55000 +\set VERBOSITY default +SELECT active FROM pg_replication_slots WHERE slot_name = 'regress_subxact_slot'; + active +-------- + f +(1 row) + +SELECT count(*) >= 0 AS peek_ok + FROM pg_logical_slot_peek_changes('regress_subxact_slot', NULL, NULL); + peek_ok +--------- + t +(1 row) + +SELECT pg_drop_replication_slot('regress_subxact_slot'); + pg_drop_replication_slot +-------------------------- + +(1 row) + +-- An error caught by a PL/pgSQL exception block releases the session's +-- temporary slot, but does not drop it (unlike a top-level error). +SELECT 'init' FROM pg_create_logical_replication_slot('regress_subxact_temp_slot', 'test_decoding', true); + ?column? +---------- + init +(1 row) + +DO $$ +BEGIN + PERFORM pg_replication_slot_advance('regress_subxact_temp_slot', '0/1'); +EXCEPTION WHEN OTHERS THEN + RAISE NOTICE 'caught SQLSTATE %', SQLSTATE; +END $$; +NOTICE: caught SQLSTATE 55000 +SELECT count(*) = 1 AS temp_slot_kept + FROM pg_replication_slots WHERE slot_name = 'regress_subxact_temp_slot'; + temp_slot_kept +---------------- + t +(1 row) + +SELECT pg_drop_replication_slot('regress_subxact_temp_slot'); + pg_drop_replication_slot +-------------------------- + +(1 row) + diff --git a/contrib/test_decoding/sql/slot.sql b/contrib/test_decoding/sql/slot.sql index 50a950341fc..021280ebe3e 100644 --- a/contrib/test_decoding/sql/slot.sql +++ b/contrib/test_decoding/sql/slot.sql @@ -193,3 +193,49 @@ SELECT pg_drop_replication_slot('failover_true_slot'); SELECT pg_drop_replication_slot('failover_false_slot'); SELECT pg_drop_replication_slot('failover_default_slot'); SELECT pg_drop_replication_slot('physical_slot'); + +-- +-- Test that a replication slot gets released when the subtransaction holding +-- it aborts on an error caught by a PL/pgSQL exception block. +-- + +SELECT 'init' FROM pg_create_logical_replication_slot('regress_subxact_slot', 'test_decoding'); + +-- An error caught by a PL/pgSQL exception block releases the slot. +DO $$ +BEGIN + PERFORM pg_replication_slot_advance('regress_subxact_slot', '0/1'); +EXCEPTION WHEN OTHERS THEN + RAISE NOTICE 'caught SQLSTATE %', SQLSTATE; +END $$; +SELECT active FROM pg_replication_slots WHERE slot_name = 'regress_subxact_slot'; +SELECT count(*) >= 0 AS peek_ok + FROM pg_logical_slot_peek_changes('regress_subxact_slot', NULL, NULL); + +-- An error not caught by a PL/pgSQL exception block releases the slot too. +-- Show only the SQLSTATE for stable output. +\set VERBOSITY sqlstate +DO $$ +BEGIN + PERFORM pg_replication_slot_advance('regress_subxact_slot', '0/1'); +EXCEPTION WHEN division_by_zero THEN + RAISE NOTICE 'unreachable'; +END $$; +\set VERBOSITY default +SELECT active FROM pg_replication_slots WHERE slot_name = 'regress_subxact_slot'; +SELECT count(*) >= 0 AS peek_ok + FROM pg_logical_slot_peek_changes('regress_subxact_slot', NULL, NULL); +SELECT pg_drop_replication_slot('regress_subxact_slot'); + +-- An error caught by a PL/pgSQL exception block releases the session's +-- temporary slot, but does not drop it (unlike a top-level error). +SELECT 'init' FROM pg_create_logical_replication_slot('regress_subxact_temp_slot', 'test_decoding', true); +DO $$ +BEGIN + PERFORM pg_replication_slot_advance('regress_subxact_temp_slot', '0/1'); +EXCEPTION WHEN OTHERS THEN + RAISE NOTICE 'caught SQLSTATE %', SQLSTATE; +END $$; +SELECT count(*) = 1 AS temp_slot_kept + FROM pg_replication_slots WHERE slot_name = 'regress_subxact_temp_slot'; +SELECT pg_drop_replication_slot('regress_subxact_temp_slot'); diff --git a/doc/src/sgml/func/func-admin.sgml b/doc/src/sgml/func/func-admin.sgml index 64b0e7bb972..f7d943234a7 100644 --- a/doc/src/sgml/func/func-admin.sgml +++ b/doc/src/sgml/func/func-admin.sgml @@ -1051,7 +1051,9 @@ postgres=# SELECT '0/0'::pg_lsn + pd.segment_number * ps.setting::int + :offset parameter, temporary, when set to true, specifies that the slot should not be permanently stored to disk and is only meant for use by the current session. Temporary slots are also - released upon any error. This function corresponds + dropped when an error is reported. An error caught inside a + subtransaction, for example by a PL/pgSQL + exception block, does not drop them. This function corresponds to the replication protocol command CREATE_REPLICATION_SLOT ... PHYSICAL. @@ -1091,7 +1093,9 @@ postgres=# SELECT '0/0'::pg_lsn + pd.segment_number * ps.setting::int + :offset parameter, temporary, when set to true, specifies that the slot should not be permanently stored to disk and is only meant for use by the current session. Temporary slots are also - released upon any error. The optional fourth parameter, + dropped when an error is reported. An error caught inside a + subtransaction, for example by a PL/pgSQL + exception block, does not drop them. The optional fourth parameter, twophase, when set to true, specifies that the decoding of prepared transactions is enabled for this slot. The optional fifth parameter, diff --git a/doc/src/sgml/protocol.sgml b/doc/src/sgml/protocol.sgml index 8ced69f283b..ae1a04b3454 100644 --- a/doc/src/sgml/protocol.sgml +++ b/doc/src/sgml/protocol.sgml @@ -2371,7 +2371,10 @@ psql "dbname=postgres replication=database" -c "IDENTIFY_SYSTEM;" Specify that this replication slot is a temporary one. Temporary slots are not saved to disk and are automatically dropped on error - or when the session has finished. + or when the session has finished. An error raised and caught in a + subtransaction, for example by a + PL/pgSQL exception block, does not drop + them. diff --git a/doc/src/sgml/system-views.sgml b/doc/src/sgml/system-views.sgml index 77202e2c765..efefc43e6fc 100644 --- a/doc/src/sgml/system-views.sgml +++ b/doc/src/sgml/system-views.sgml @@ -2894,7 +2894,10 @@ SELECT * FROM pg_locks pl LEFT JOIN pg_prepared_xacts ppx True if this is a temporary replication slot. Temporary slots are not saved to disk and are automatically dropped on error or when - the session has finished. + the session has finished. An error raised and caught in a + subtransaction, for example by a + PL/pgSQL exception block, does not drop + them. diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c index ebb010853cf..4f1a91c1965 100644 --- a/src/backend/access/transam/xact.c +++ b/src/backend/access/transam/xact.c @@ -5205,6 +5205,7 @@ CommitSubTransaction(void) s->parent->curTransactionOwner); AtEOSubXact_LargeObject(true, s->subTransactionId, s->parent->subTransactionId); + AtEOSubXact_ReplicationSlot(true, s->subTransactionId); AtSubCommit_Notify(); CallSubXactCallbacks(SUBXACT_EVENT_COMMIT_SUB, s->subTransactionId, @@ -5382,6 +5383,7 @@ AbortSubTransaction(void) s->parent->curTransactionOwner); AtEOSubXact_LargeObject(false, s->subTransactionId, s->parent->subTransactionId); + AtEOSubXact_ReplicationSlot(false, s->subTransactionId); AtSubAbort_Notify(); /* Advertise the fact that we aborted in pg_xact. */ diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 63ce6d27885..45766541bed 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -59,6 +59,7 @@ #include "utils/builtins.h" #include "utils/guc_hooks.h" #include "utils/injection_point.h" +#include "utils/snapmgr.h" #include "utils/varlena.h" #include "utils/wait_event.h" @@ -157,6 +158,13 @@ const ShmemCallbacks ReplicationSlotsShmemCallbacks = { /* My backend's replication slot in the shared memory array */ ReplicationSlot *MyReplicationSlot = NULL; +/* + * Subxact that acquired MyReplicationSlot, or invalid if none is held + * or it was acquired with no transaction in progress (as a walsender does). + * Used to release the slot when that subxact aborts. + */ +static SubTransactionId MyReplicationSlotSubId = InvalidSubTransactionId; + /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ @@ -519,6 +527,7 @@ ReplicationSlotCreate(const char *name, bool db_specific, slot->active_proc = MyProcNumber; SpinLockRelease(&slot->mutex); MyReplicationSlot = slot; + MyReplicationSlotSubId = GetCurrentSubTransactionId(); LWLockRelease(ReplicationSlotControlLock); @@ -724,6 +733,7 @@ retry: /* We made this slot active, so it's ours now. */ MyReplicationSlot = s; + MyReplicationSlotSubId = GetCurrentSubTransactionId(); /* * We need to check for invalidation after making the slot ours to avoid @@ -848,6 +858,61 @@ ReplicationSlotRelease(void) pfree(slotname); } + + /* The slot is no longer acquired in any subxact. */ + MyReplicationSlotSubId = InvalidSubTransactionId; +} + +/* + * At subxact end, release the replication slot if the subtransaction + * where the slot was acquired is aborted. + */ +void +AtEOSubXact_ReplicationSlot(bool isCommit, SubTransactionId mySubid) +{ + /* Nothing to do unless the slot was acquired in this subxact. */ + if (MyReplicationSlotSubId != mySubid) + return; + + /* + * The subxact that acquired the slot is committing with the slot still + * held. No slot function in the core code does that today, though an + * extension might. A slot left unreleased by mistake cannot be told apart + * from one the caller means to release later. Leave it to the caller. + */ + if (isCommit) + { + MyReplicationSlotSubId = InvalidSubTransactionId; + return; + } + + /* + * We must not get here while decoding is running. Decoding starts and + * aborts an internal (sub)transaction while holding the slot, for each + * decoded transaction (ReorderBufferProcessTXN()) and when executing + * invalidations (ReorderBufferImmediateInvalidation()). However, those + * subtransactions are always nested below the one that acquired the slot, + * so their subtransaction ids are deeper and do not match here. Decoding + * also runs with a historic snapshot set up, so assert that it is not. + */ + Assert(!HistoricSnapshotActive()); + + /* + * The aborting subxact is the one that acquired the slot, so the slot is + * still held and must be released. MyReplicationSlotSubId is set only + * when a slot is held and cleared when it is released, so a matching + * subxact id means the slot is ours. + * + * We only release the slot here and do not drop the session's temporary + * slots, unlike the top-level error handler in PostgresMain(). An error + * caught within a subtransaction, for example by a PL/pgSQL exception + * block, is normally meant to be handled so the session carries on, + * unlike a top-level error, so a temporary slot is left in place. That + * matches the temporary slot behavior that predates this callback and is + * simpler to reason about; the slot lives on until the session ends or a + * top-level error occurs, as documented. + */ + ReplicationSlotRelease(); } /* @@ -1042,6 +1107,7 @@ ReplicationSlotDropAcquired(bool try_disable) /* slot isn't acquired anymore */ MyReplicationSlot = NULL; + MyReplicationSlotSubId = InvalidSubTransactionId; ReplicationSlotDropPtr(slot); diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c index b6bdfe213fe..a2f72f9eb5b 100644 --- a/src/backend/tcop/postgres.c +++ b/src/backend/tcop/postgres.c @@ -4638,7 +4638,9 @@ PostgresMain(const char *dbname, const char *username) * need to be able to start and abort transactions while having a slot * acquired. But we never need to hold them across top level errors, * so releasing here is fine. There also is a before_shmem_exit() - * callback ensuring correct cleanup on FATAL errors. + * callback for FATAL errors, and AtEOSubXact_ReplicationSlot() for an + * error caught in a subtransaction. The latter only releases the slot + * and, unlike here, does not drop the session's temporary slots. */ if (MyReplicationSlot != NULL) ReplicationSlotRelease(); diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 9b29444cbca..171ba6f2318 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -343,6 +343,7 @@ extern void ReplicationSlotAcquire(const char *name, bool nowait, bool error_if_invalid); extern void ReplicationSlotRelease(void); extern void ReplicationSlotCleanup(bool synced_only); +extern void AtEOSubXact_ReplicationSlot(bool isCommit, SubTransactionId mySubid); extern void ReplicationSlotSave(void); extern void ReplicationSlotMarkDirty(void); -- 2.47.3